Stirling cryocooler test method and device, cryocooler test equipment and medium
By constructing a refrigerator reliability prediction model based on the Catboost algorithm, the problem of long refrigeration machine detection cycle in the existing technology is solved, and fast and accurate judgment of the refrigerator test results is achieved, and production efficiency is improved.
Patent Information
- Application Number
- CN202411993483.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-31
- Publication Date
- 2025-04-25
AI Technical Summary
The existing Stirling refrigerator performance detection system has a long inspection cycle and cannot screen out unqualified refrigerators in time.
By obtaining the refrigerator test parameter set, correcting and constructing target parameter characteristics, the target refrigerator reliability prediction model is constructed based on the optimized Catboost algorithm, which is used to quickly judge the high and low temperature test results of the refrigerator.
It effectively shortens the detection cycle of the refrigerator, can timely screen out unqualified refrigerators, and improves testing accuracy and production efficiency.
Smart Images
Figure CN119880477A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of refrigerator detection technology, and in particular to a Stirling refrigerator testing method, device, refrigerator testing equipment and medium. Background Art
[0002] The integral Stirling rotary refrigerator mainly provides an effective cooling source for the low-temperature detector. In order to ensure the stable operation of each refrigerator, a large number of tests are required on the refrigerator.
[0003] The existing Stirling refrigerator performance detection system mainly makes judgments through running-in tests and high and low temperature tests. The detection cycle is long and it is impossible to screen out unqualified machines in time. Summary of the invention
[0004] In order to solve the above technical problems, the embodiments of the present application provide a Stirling refrigerator testing method, device, refrigerator testing equipment and medium that can effectively shorten the refrigerator testing cycle and timely screen out unqualified machines. The specific scheme is as follows: In a first aspect, an embodiment of the present application provides a Stirling refrigerator testing method, comprising: Get the refrigerator test parameter set; Correcting the refrigerator test parameter set and constructing target parameter features; Performing model training according to the revised refrigerator test parameter set and target parameter characteristics to obtain a target refrigerator reliability prediction model, wherein the target refrigerator reliability prediction model is constructed based on an optimized Catboost algorithm; The test parameter set and target parameter characteristics of the refrigerator to be tested are input into the target refrigerator reliability prediction model to obtain the target test result.
[0005] According to a specific implementation of the embodiment of the present application, obtaining a refrigerator test parameter set includes: Start the refrigerator to be tested; Controlling the ambient temperature of the refrigerator to be tested to be a target temperature; Control the refrigerator to be tested to run in for a first time, and wait for a second time to perform a performance test after the running-in is completed to obtain the refrigerator test parameter set, wherein the performance test is maintained for a third time, wherein the first time is greater than the second time, and the second time is greater than the third time.
[0006] According to a specific implementation of an embodiment of the present application, the refrigerator test parameter set includes the refrigerator normal temperature running-in current, normal temperature running-in speed, normal temperature running-in coke temperature, performance test current, performance test speed, performance test coke temperature, return to temperature time and frequency reduction time.
[0007] According to a specific implementation of the embodiment of the present application, the correction processing of the refrigerator test parameter set includes: Standardizing the data in the refrigerator test parameter set to obtain a standard test data set; Using a K-means clustering algorithm to optimize parameters of the standard test data set to obtain an optimized test data set; Calculating respectively the corrected average values of the test parameters of each refrigerator according to the standard test data set and the optimized test data set; The parameters in the refrigerator test parameter set are corrected according to the corrected average value to obtain a corrected refrigerator test parameter set.
[0008] According to a specific implementation of the embodiment of the present application, the constructing target parameter features includes: Acquire the first target parameter data of the refrigerator to be tested at a preset time after the refrigerator to be tested starts running-in, and the second target parameter data of the refrigerator to be tested at a preset time before the refrigerator to be tested ends running-in; The target parameter feature is constructed according to the first target parameter data and the second target parameter data, wherein the target parameter feature is a difference feature.
[0009] According to a specific implementation of the embodiment of the present application, the constructing target parameter features includes: Acquire first speed data of the refrigerator to be tested at a first preset time after the refrigerator to be tested starts running-in, and second speed data of the refrigerator to be tested at a first preset time before the refrigerator to be tested ends running-in; constructing a speed difference feature according to the first speed data and the second speed data; Acquire the first stable current data of the refrigerator to be tested a second preset time after the refrigerator to be tested starts running-in, and the second stable current data of the refrigerator to be tested a second preset time before the refrigerator to be tested ends running-in; The stable current difference feature is constructed according to the first stable current data and the second stable current data.
[0010] According to a specific implementation of the embodiment of the present application, the model training is performed according to the modified refrigerator test parameter set and the target parameter characteristics to obtain the target refrigerator reliability prediction model, including: Building an initial prediction model based on the Catboost algorithm, wherein the initial prediction model uses the refrigerator test parameter set and the target parameter characteristics as input parameters and uses whether the refrigerator is reliable as the output result; The Catboost algorithm parameters are optimized by GridSearchCV to select the optimal model training parameters, wherein the Catboost algorithm parameters include the maximum number of trees, learning rate, maximum depth of the tree, maximum number of leaf nodes, and minimum sample size of leaf nodes; The modified refrigerator test parameter set is divided into a training set and a test set, and a preset multiple cross validation is completed according to the optimal model training parameters to obtain the target refrigerator reliability prediction model.
[0011] In a second aspect, an embodiment of the present application provides a Stirling refrigerator testing device, comprising: An acquisition module, used for acquiring a refrigerator test parameter set; A correction module, used for correcting the refrigerator test parameter set and constructing target parameter characteristics; A training module, used for performing model training according to the modified refrigerator test parameter set and target parameter characteristics to obtain a target refrigerator reliability prediction model, wherein the target refrigerator reliability prediction model is constructed based on an optimized Catboost algorithm; The prediction module is used to input the test parameter set and target parameter characteristics of the refrigerator to be tested into the reliability prediction model of the target refrigerator to obtain the target test result.
[0012] In a third aspect, an embodiment of the present application provides a refrigerator testing device, the refrigerator testing device comprising: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the Stirling refrigerator testing method described in the first aspect.
[0013] In a fourth aspect, an embodiment of the present application further provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the Stirling refrigerator testing method described in the first aspect.
[0014] In summary, the present embodiment provides a Stirling refrigerator test method, device, refrigerator test equipment and medium, including: obtaining a refrigerator test parameter set; correcting the refrigerator test parameter set and constructing a target parameter feature; performing model training according to the corrected refrigerator test parameter set and the target parameter feature to obtain a target refrigerator reliability prediction model, wherein the target refrigerator reliability prediction model is constructed based on the optimized Catboost algorithm; inputting the test parameter set and the target parameter feature of the refrigerator to be tested into the target refrigerator reliability prediction model to obtain a target test result. The present application constructs a target refrigerator reliability prediction model through the optimized Catboost algorithm, and can predict the high and low temperature test results of the refrigerator based on experimental test data, thereby effectively judging whether the refrigerator is qualified, shortening the refrigerator test time, and improving the refrigerator test accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0016] Figure 1 A schematic diagram of a flow chart of a Stirling refrigerator testing method provided in an embodiment of the present application; Figure 2 A schematic diagram of the steps for obtaining a refrigerator test parameter set provided in an embodiment of the present application; Figure 3 A schematic diagram of the steps for correcting a refrigerator test parameter set provided in an embodiment of the present application; Figure 4 A schematic diagram of the effect of screening outliers based on the K-means clustering algorithm provided in an embodiment of the present application; Figure 5 A schematic diagram of the steps for constructing target parameter features provided in an embodiment of the present application; Figure 6 A schematic diagram of the steps of constructing a target refrigerator reliability prediction model provided in an embodiment of the present application; Figure 7 A module schematic diagram of a Stirling refrigerator testing device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0017] The embodiments of the present application are described in detail below with reference to the accompanying drawings.
[0018] The following describes the implementation methods of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the following embodiments and the features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.
[0019] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present application, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.
[0020] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. The drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.
[0021] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.
[0022] refer to Figure 1 The present application provides a Stirling refrigerator testing method, which is described by taking the method applied to a refrigerator testing device as an example, and includes the following steps: S101, obtaining a refrigerator test parameter set.
[0023] S102, correcting the refrigerator test parameter set and constructing target parameter features.
[0024] S103, performing model training according to the modified refrigerator test parameter set and the target parameter characteristics to obtain a target refrigerator reliability prediction model, wherein the target refrigerator reliability prediction model is constructed based on the optimized Catboost algorithm.
[0025] S104, inputting the test parameter set and target parameter characteristics of the refrigerator to be tested into a target refrigerator reliability prediction model to obtain a target test result.
[0026] In this embodiment, the refrigerator test parameter set is a data set composed of multiple refrigerator experimental parameters. For example, the refrigerator test parameter set includes data such as refrigerator normal temperature running-in current, normal temperature running-in speed, normal temperature running-in coke temperature, performance test current, performance test speed, performance test coke temperature, temperature recovery time and frequency reduction time. It should be noted that the refrigerator test parameter set can be a test parameter set of the refrigerator to be tested, or it can be a test parameter set of the refrigerator used to train the model. The method for obtaining the refrigerator test parameter set can be determined according to the specific configuration of the laboratory in the actual application scenario.
[0027] After obtaining the refrigerator test parameter set, the refrigerator test parameter set is corrected to remove abnormal data in the original data, which can effectively ensure the training accuracy and prediction accuracy of the prediction model. In the actual application process, it is also necessary to construct target parameter features based on at least part of the parameters in the refrigerator test parameter set to further improve the prediction effect of the prediction model, so as to ensure that the prediction model can accurately output the high and low temperature test results of the Stirling refrigerator.
[0028] In the specific application process, the Stirling refrigerator test method provided in this embodiment is mainly used to test whether the Stirling refrigerator product is qualified. The high and low temperature test results include high temperature test results and low temperature test results. The high temperature test is to run the refrigerator at 71°C, test the coke temperature, speed, current, frequency reduction time, etc. of the refrigerator, and judge whether the operation state of the refrigerator is stable under high temperature conditions through relevant test data. The low temperature test is to run at -55°C, test the coke temperature, speed, current, frequency reduction time, etc. of the refrigerator, and judge whether the operation state of the refrigerator is stable under low temperature conditions through relevant test data.
[0029] It should be noted that the high and low temperature test results of the Stirling refrigerator will be affected by many factors, including the type of refrigerator, test conditions, input power, operating frequency, and the manufacturing accuracy and assembly quality of the refrigerator.
[0030] In this embodiment, a target refrigerator reliability prediction model is constructed based on the optimized Catboost algorithm, and the test parameter set and target parameter characteristics of the refrigerator to be tested are used as input parameters of the target refrigerator reliability prediction model, and the high and low temperature test results are used as output results of the target refrigerator reliability prediction model. The target refrigerator reliability prediction model can directly reflect the product qualification results of the refrigerator to be tested, thereby realizing rapid screening of Stirling refrigerators, greatly reducing the product testing time of Stirling refrigerators, quickly screening out unqualified machines, and effectively shortening the production cycle.
[0031] According to a specific implementation of the embodiment of the present application, Figure 2 As shown, a refrigerator test parameter set is obtained, including: S201, start the refrigerator to be tested.
[0032] S202, controlling the ambient temperature of the refrigerator to be tested to be a target temperature.
[0033] S203, controlling the refrigerator to be tested to run-in for a first time, and waiting for a second time to perform a performance test after the running-in is completed, so as to obtain a refrigerator test parameter set, wherein the performance test is maintained for a third time, wherein the first time is greater than the second time, and the second time is greater than the third time.
[0034] In this embodiment, the refrigerator test equipment includes a main control unit, a power supply unit, an ambient temperature control unit and a performance test unit, wherein the power supply unit is connected to the product test station, and the power supply unit, the ambient temperature control unit and the performance test unit are all connected to the main control unit. In actual application, the refrigerator to be tested is placed in the product test station, and the refrigerator test equipment can be used to perform product testing on the refrigerator to be tested.
[0035] In this embodiment, the refrigeration machine to be tested on the product testing station can be started by controlling the power supply unit of the refrigeration machine testing equipment to adjust the DC power supply output voltage to the target power supply voltage. The target power supply voltage can be determined according to the actual type of the refrigeration machine to be tested in the actual application scenario. For example, the target power supply voltage can be 24V.
[0036] In this embodiment, the target temperature can be configured according to the needs of the actual application scenario. For example, the ambient temperature control unit can be controlled to adjust the ambient temperature of the refrigerator to be tested to 23 degrees Celsius (°C). It should be noted that the ambient temperature control unit can be a temperature control box or other temperature adjustment equipment.
[0037] In a feasible embodiment, the refrigerator to be tested can be controlled to run-in for 48 hours (h), then the refrigerator to be tested can be controlled to stop and wait for 4 hours, and after the refrigerator to be tested is stopped and cooled for 4 hours, a performance test step of 20 minutes (min) is performed. It should be noted that the performance test step in this embodiment is the same as the refrigerator experimental test step in the related art.
[0038] This embodiment obtains the original data of the refrigerator test data set through the performance test step.
[0039] According to a specific implementation of the embodiment of the present application, Figure 3 As shown, the refrigerator test parameter set is modified, including: S301, standardize the data in the refrigerator test parameter set to obtain a standard test data set.
[0040] S302, using a K-means clustering algorithm to optimize parameters of a standard test data set to obtain an optimized test data set.
[0041] S303, calculating the corrected average values of the test parameters of each refrigerator respectively according to the standard test data set and the optimized test data set.
[0042] S304, correcting the parameters in the refrigerator test parameter set according to the corrected average value to obtain a corrected refrigerator test parameter set.
[0043] In this embodiment, the refrigerator test parameter set is obtained. , the refrigerator test parameter set is transformed according to the following formula: in, is the refrigerator test parameter, , is a positive integer, , .
[0044] According to the above formula, the standard test data set can be obtained .
[0045] Use K-means clustering algorithm to cluster the standard test data set Clustering. The K-Means clustering algorithm is an unsupervised learning algorithm that iteratively divides cluster centers and redistributes them according to the Euclidean distance between cluster centers and data points to divide the original sample data into multiple new clusters, ensuring that the data in each cluster is more similar, thereby screening valid data and abnormal data. By setting the convergence condition, the limited iteration of the K-Means clustering algorithm is achieved.
[0046] In this embodiment, outlier detection is mainly achieved by using the K-means clustering algorithm. The K-means clustering algorithm separates the original experimental data in the standard test parameter set and re-segments them into the most similar The steps are as follows: Step 1: Set the clustering data volume to The data set has the number of clusters , the initial cluster center is .
[0047] Step 2: Take data from the standard test parameter set one by one and calculate the difference between all data points and the initial selection. The Euclidean distance of the cluster centers is calculated according to the result of the Euclidean distance. The samples are divided into the nearest center point, and finally generated Specifically, the calculation formula of Euclidean distance is: in, ——No. The cluster centers of the clusters, is the sample data in the standard test parameter set, For the The cluster center of the cluster data, The first data.
[0048] Step 3: Calculate the mean points of all elements in each category, and use the mean points obtained as the new cluster center of each category. .
[0049] Step 4: Compare The mean point and The mean points of the new cluster centers are the same. If they are the same, the K-Means clustering algorithm ends. If they are different, the iteration steps 1 and 3 are repeated until the mean point of the new cluster center is the same as the mean point of the cluster center before the update or is less than the specified threshold, and the K-Means clustering algorithm ends.
[0050] The outliers that are not classified into the cluster center are regarded as data outliers. The data outliers are eliminated to obtain the optimized test data set.
[0051] Finally, based on the first data value in the standard test data set and the second data value in the optimized test data set, the average of the first data value and the second data value is calculated to obtain a corrected average value, so as to update and correct the data in the test parameter set to obtain the corrected test parameters, thereby ensuring that the data is valid and authentic.
[0052] In summary, the clustering results of the K-Means clustering algorithm are as follows Figure 4 As shown, multiple new clusters can be divided from different dimensions, and outliers in the test parameter set can be effectively proposed, thereby realizing parameter correction of the test parameter set, ensuring the prediction effect of the subsequent test model, and being able to truly reflect the actual performance of the refrigerator.
[0053] A specific implementation of the embodiment of the present application is as follows Figure 5 As shown, construct the target parameter features, including: S501, obtaining first target parameter data of a preset time after the refrigerator to be tested starts running-in, and second target parameter data of a preset time before the refrigerator to be tested ends running-in; S502: construct a target parameter feature according to the first target parameter data and the second target parameter data, wherein the target parameter feature is a difference feature.
[0054] In this embodiment, the target parameter characteristics include a rotation speed difference characteristic and a stable current difference characteristic. It should be noted that the target parameter characteristics can also be configured with other parameter difference characteristics according to the needs of the actual application scenario.
[0055] In actual application, the steps to construct target parameter features include: The first speed data of the refrigerator to be tested at the first preset time after the refrigerator to be tested starts running-in and the second speed data of the refrigerator to be tested at the first preset time before the refrigerator to be tested ends running-in are obtained. The speed difference feature is constructed based on the first speed data and the second speed data.
[0056] The first stable current data of the refrigerator to be tested at a second preset time after the refrigerator to be tested starts running-in and the second stable current data of the refrigerator to be tested at a second preset time before the refrigerator to be tested ends running-in are obtained. A stable current difference feature is constructed based on the first stable current data and the second stable current data.
[0057] In this embodiment, the first preset time and the second preset time may be the same or different, and the specific values of the first preset time and the second preset time may be configured according to the needs of the actual application scenario. For example, the first preset time and the second preset time may both be set to 10 minutes, or the first preset time may be set to 10 minutes and the second preset time may be set to 15 minutes.
[0058] According to a specific implementation of the embodiment of the present application, Figure 6 As shown, the model training is performed according to the modified refrigerator test parameter set and the target parameter characteristics to obtain the target refrigerator reliability prediction model, including: S601, building an initial prediction model based on the Catboost algorithm, wherein the initial prediction model uses the refrigerator test parameter set and the target parameter characteristics as input parameters, and uses whether the refrigerator is reliable as the output result.
[0059] S602, optimizing the parameters of the Catboost algorithm through GridSearchCV to select the optimal model training parameters, wherein the Catboost algorithm parameters include the maximum number of trees, the learning rate, the maximum depth of the tree, the maximum number of leaf nodes, and the minimum sample size of leaf nodes.
[0060] S603, dividing the modified refrigerator test parameter set into a training set and a test set, completing a preset multiple cross validation according to the optimal model training parameters, and obtaining a target refrigerator reliability prediction model.
[0061] In this embodiment, CatBoost (Categorical Boosting) is a gradient boosting decision tree (GBDT) algorithm that specifically optimizes the ability to process categorical features and sequence data. The Catboost algorithm can iteratively construct a decision tree and process refrigerator parameter sets and target parameter features based on a symmetric tree structure, which can help efficient CPU implementation, reduce prediction time, prevent overfitting, and achieve fast, high-precision high and low temperature reliability testing.
[0062] In this embodiment, the cross-validation multiple can be set to 10, or can be configured to other multiples according to the needs of actual application scenarios.
[0063] In summary, the present embodiment provides a Stirling refrigerator testing method, which can effectively perform experimental tests on an integral rotary Stirling refrigerator through experimental parameter settings. By experimentally testing the normal temperature running-in current, rotation speed, coke temperature data, and the performance test current, rotation speed, coke temperature, temperature recovery time, and frequency reduction time data, the high and low temperature experimental results of the integral Stirling rotary refrigerator are predicted. The prediction accuracy is high, and the high and low temperature test results of the refrigerator can be effectively judged in advance, thereby shortening the environmental experiment time and production cycle of the refrigerator, and greatly saving the production cost of the refrigerator.
[0064] Based on the same inventive concept, the embodiment of the present application also provides a Stirling refrigerator test device for implementing the Stirling refrigerator test method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more Stirling refrigerator test device embodiments provided below can refer to the limitations of the Stirling refrigerator test method above, and will not be repeated here.
[0065] In one embodiment, reference Figure 7 This embodiment also provides a Stirling refrigerator testing device 700, including: an acquisition module 710, a correction module 720, a training module 730 and a prediction module 740, wherein: An acquisition module 710 is used to acquire a refrigerator test parameter set; A correction module 720, used to correct the refrigerator test parameter set and construct a target parameter feature; A training module 730 is used to perform model training according to the modified refrigerator test parameter set and the target parameter characteristics to obtain a target refrigerator reliability prediction model, wherein the target refrigerator reliability prediction model is constructed based on the optimized Catboost algorithm; The prediction module 740 is used to input the test parameter set and target parameter characteristics of the refrigerator to be tested into the target refrigerator reliability prediction model to obtain the target test result.
[0066] In summary, the present embodiment provides a Stirling refrigerator testing device, which can effectively perform experimental tests on the integral rotary Stirling refrigerator through experimental parameter settings, and predict the high and low temperature experimental results of the integral Stirling rotary refrigerator through experimental testing of normal temperature running-in current, rotation speed, coke temperature data, and performance test current, rotation speed, coke temperature, temperature recovery time, and frequency reduction time data. The prediction accuracy is high, and the high and low temperature test results of the refrigerator can be effectively judged in advance, shortening the environmental experiment time and production cycle of the refrigerator, and greatly saving the production cost of the refrigerator.
[0067] In addition, the embodiment of the present application further provides a refrigerator testing device, the refrigerator testing device comprising: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the Stirling refrigerator testing method in the aforementioned method embodiment.
[0068] An embodiment of the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the Stirling refrigerator testing method in the aforementioned method embodiment.
[0069] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.
[0070] In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0071] The computer-readable medium may be included in the refrigerator testing device; or may exist independently without being assembled into the refrigerator testing device.
[0072] The computer-readable medium carries one or more programs. When the one or more programs are executed by the refrigerator test device, the refrigerator test device: obtains a refrigerator test parameter set. Corrects the refrigerator test parameter set and constructs a target parameter feature. Model training is performed based on the corrected refrigerator test parameter set and the target parameter feature to obtain a target refrigerator reliability prediction model, wherein the target refrigerator reliability prediction model is constructed based on the optimized Catboost algorithm. The test parameter set and the target parameter feature of the refrigerator to be tested are input into the target refrigerator reliability prediction model to obtain a target test result.
[0073] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0074] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A Stirling refrigerator testing method, characterized in that: include: Get the refrigerator test parameter set; Correcting the refrigerator test parameter set and constructing target parameter features; Performing model training according to the revised refrigerator test parameter set and target parameter characteristics to obtain a target refrigerator reliability prediction model, wherein the target refrigerator reliability prediction model is constructed based on an optimized Catboost algorithm; The test parameter set and target parameter characteristics of the refrigerator to be tested are input into the target refrigerator reliability prediction model to obtain the target test result.
2. The method according to claim 1, characterized in that Get the chiller test parameter set, including: Start the refrigerator to be tested; Controlling the ambient temperature of the refrigerator to be tested to be a target temperature; Control the refrigerator to be tested to run in for a first time, and wait for a second time to perform a performance test after the running-in is completed to obtain the refrigerator test parameter set, wherein the performance test is maintained for a third time, wherein the first time is greater than the second time, and the second time is greater than the third time.
3. The method according to claim 2, characterized in that The refrigerator test parameter set includes refrigerator normal temperature running-in current, normal temperature running-in speed, normal temperature running-in coke temperature, performance test current, performance test speed, performance test coke temperature, temperature recovery time and frequency reduction time.
4. The method according to claim 1, characterized in that The correcting process of the refrigerator test parameter set includes: Standardizing the data in the refrigerator test parameter set to obtain a standard test data set; Using a K-means clustering algorithm to optimize parameters of the standard test data set to obtain an optimized test data set; Calculating respectively the corrected average values of the test parameters of each refrigerator according to the standard test data set and the optimized test data set; The parameters in the refrigerator test parameter set are corrected according to the corrected average value to obtain a corrected refrigerator test parameter set.
5. The method according to claim 3, characterized in that: The construction target parameter features include: Acquire the first target parameter data of the refrigerator to be tested at a preset time after the refrigerator to be tested starts running-in, and the second target parameter data of the refrigerator to be tested at a preset time before the refrigerator to be tested ends running-in; The target parameter feature is constructed according to the first target parameter data and the second target parameter data, wherein the target parameter feature is a difference feature.
6. The method according to claim 5, characterized in that The construction target parameter features include: Acquire first speed data of the refrigerator to be tested at a first preset time after the refrigerator to be tested starts running-in, and second speed data of the refrigerator to be tested at a first preset time before the refrigerator to be tested ends running-in; constructing a speed difference feature according to the first speed data and the second speed data; Acquire the first stable current data of the refrigerator to be tested a second preset time after the refrigerator to be tested starts running-in, and the second stable current data of the refrigerator to be tested a second preset time before the refrigerator to be tested ends running-in; The stable current difference feature is constructed according to the first stable current data and the second stable current data.
7. The method according to claim 1, characterized in that The model training is performed according to the modified refrigerator test parameter set and the target parameter characteristics to obtain the target refrigerator reliability prediction model, including: Building an initial prediction model based on the Catboost algorithm, wherein the initial prediction model uses the refrigerator test parameter set and the target parameter characteristics as input parameters and uses whether the refrigerator is reliable as the output result; The Catboost algorithm parameters are optimized by GridSearchCV to select the optimal model training parameters, wherein the Catboost algorithm parameters include the maximum number of trees, learning rate, maximum depth of the tree, maximum number of leaf nodes, and minimum sample size of leaf nodes; The modified refrigerator test parameter set is divided into a training set and a test set, and a preset multiple cross validation is completed according to the optimal model training parameters to obtain the target refrigerator reliability prediction model.
8. A Stirling refrigerator testing device, characterized in that: include: An acquisition module, used for acquiring a refrigerator test parameter set; A correction module, used for correcting the refrigerator test parameter set and constructing target parameter characteristics; A training module, used for performing model training according to the modified refrigerator test parameter set and target parameter characteristics to obtain a target refrigerator reliability prediction model, wherein the target refrigerator reliability prediction model is constructed based on an optimized Catboost algorithm; The prediction module is used to input the test parameter set and target parameter characteristics of the refrigerator to be tested into the reliability prediction model of the target refrigerator to obtain the target test result.
9. A refrigerator testing device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the Stirling refrigerator testing method according to any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the Stirling refrigerator testing method according to any one of claims 1 to 7.